The London School of Hygiene & Tropical Medicine in the UK recently released a communique announcing the findings of a randomized controlled trial. The trial, which involved the school, demonstrated that integrating AI technology into diabetic retinopathy screening significantly reduced the time it took for patients to progress from screening to specialist consultation. This, in turn, facilitated more patients in seeking prompt medical attention. The trial was carried out across 24 hospitals in Tanzania and involved 2,378 participants who were randomly allocated to either an AI-assisted screening group or a conventional screening group.

The results revealed that 35.9% of participants in the AI-assisted screening group consulted an ophthalmologist within 8 weeks, a stark contrast to the mere 18.2% in the conventional screening group. Furthermore, the average time from screening to consultation was notably shorter in the AI-assisted group, at 10.9 days, compared to 36.9 days in the conventional group. Researchers attribute this efficiency to the AI-assisted screening's ability to deliver immediate results, enabling healthcare professionals to offer face-to-face consultation advice promptly. In contrast, conventional screening relies on manual image evaluation, leading to slower feedback.

The relevant research paper has been published in The Lancet Global Health.